Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5451 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.3638. Min Act: -0.1700
Data Index: 3308068 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.2388. Min Act: -0.1700
Data Index: 6563445 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.1763. Min Act: -0.1700
Data Index: 2694334 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.1763. Min Act: -0.1700
Data Index: 905181 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.1451. Min Act: -0.1700
Data Index: 2082864 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.1451. Min Act: -0.1700
Data Index: 3752740 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.1138. Min Act: -0.1700
Data Index: 1531960 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.1138. Min Act: -0.1700
Data Index: 6242050 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.0826. Min Act: -0.1700
Data Index: 6686446 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.0826. Min Act: -0.1700
Data Index: 8646227 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.0513. Min Act: -0.1700
Data Index: 4014145 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.0513. Min Act: -0.1700
Data Index: 82910 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.0513. Min Act: -0.1700
Data Index: 5126183 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.0201. Min Act: -0.1700
Data Index: 1508200 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.0201. Min Act: -0.1700
Data Index: 8624485 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.0201. Min Act: -0.1700
Data Index: 2793468 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3638. Min Range: -6.3638
Max Act: 6.0201. Min Act: -0.1700
Data Index: 1297394 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3638. Min Range: -6.3638
Max Act: 5.9888. Min Act: -0.1700
Data Index: 3525543 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3638. Min Range: -6.3638
Max Act: 5.9576. Min Act: -0.1700
Data Index: 3011105 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3638. Min Range: -6.3638
Max Act: 5.9576. Min Act: -0.1700
Data Index: 6078071 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19